Acta mathematica scientia, Series B >
LIMITING BEHAVIOR OF RECURSIVE M-ESTIMATORS IN MULTIVARIATE LINEAR REGRESSION MODELS AND THEIR ASYMPTOTIC EFFICIENCIES
Received date: 2006-10-13
Revised date: 2007-12-10
Online published: 2010-01-20
Supported by
The research of B. Q. Miao was partially supported by the Natural Sciences and Engineering Research Council of Canada, the National Natural Science Foundation of China and the Doctorial Fund of Education Ministry of China. The research of Y. Wu was partially supported by the Natural Sciences and Engineering Research Council of Canada. The research of Donghai Liu was partially supported by the National Natural Science Foundation of China.
Recursive algorithms are very useful for computing M-estimators of regression coefficients and scatter Parameters. In this article, it is shown that for a nondecreasing u1(t), under some mild conditions the recursive M-estimators of regression coefficients and scatter parameters are strongly consistent and the recursive M-estimator of the regression coefficients is also asymptotically normal distributed. Furthermore, optimal recursive M-estimators, asymptotic efficiencies of recursive M-estimators and asymptotic relative efficiencies between recursive M-estimators of regression coefficients are studied.
MIAO Bai-Qi , WU Yue-Hua , LIU Dong-Hai . LIMITING BEHAVIOR OF RECURSIVE M-ESTIMATORS IN MULTIVARIATE LINEAR REGRESSION MODELS AND THEIR ASYMPTOTIC EFFICIENCIES[J]. Acta mathematica scientia, Series B, 2010 , 30(1) : 319 -329 . DOI: 10.1016/S0252-9602(10)60048-3
[1] Bickel P J. One-step Huber estimates in the linear model. J Amer Statist Assoc, 1975, 70: 428--434
[2] Englund J -E, Holst U, Ruppert D. Recursive M-estimate of location and scale for dependent sequences. Scand J Statist, 1988, 15: 147--159
[3] Englund J -E. Multivariate recursive M-estimate of location and scatter for dependent sequences. J Multivariate Analysis, 1993, 45: 257--273
[4] Bai Z D, Wu Y. Recursive algorithm for M-estimates of regression coefficients and scatter parameters in linear models. Sankhy={a} Ser B, 1993, 55(Part2): 199--218
[5] Miao B Q, Wu, Y. Limiting behavior of recursive M-estimators in multivariate linear regression models. J Multivariate Analysis, 1996, 59: 60--80
[6] Maronna R A. Robust estimators of multivariate location and scatter. Ann Statist, 1976, 4: 51--67
[7] Miao B Q, Wu Y, Liu D, Tong Q. Asymptotic normality of the recursive M-estimators of the scale parameters. Ann Inst Statist Math, 2006, 59: 367--384
[8] Fabian V. On asymptotic normality in stochastic approximation. Ann Math Statist, 1968, 39: 1327--1332
[9] Wu Y. On consistency of recursive multivariate M-estimators in linear models//Rieder H. Robust Statistics, Data Analysis, and Computer Intensive Methods. Lecture Notes in Statistics, Vol 109. New York: Springer-Verlag, 1996: 411--424
/
| 〈 |
|
〉 |